fix: update currentSequenceModel when modelChanged #17051
Conversation
|
Hi @adamfweidman, thank you so much for your contribution to Gemini CLI! We really appreciate the time and effort you've put into this. We're making some updates to our contribution process to improve how we track and review changes. Please take a moment to review our recent discussion post: Improving Our Contribution Process & Introducing New Guidelines. Key Update: Starting January 26, 2026, the Gemini CLI project will require all pull requests to be associated with an existing issue. Any pull requests not linked to an issue by that date will be automatically closed. Thank you for your understanding and for being a part of our community! |
Summary of ChangesHello @adamfweidman, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request refactors the model fallback mechanism to ensure consistent behavior when switching to a fallback model like Flash. Previously, the fallback model might not persist across continuations within the same conversation. The changes centralize the model activation logic within the core fallback handler, removing it from the UI layer. Crucially, the Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
|
Size Change: +226 B (0%) Total Size: 23.2 MB ℹ️ View Unchanged
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request effectively addresses the issue of fallback model persistence. The changes are well-thought-out, moving the responsibility of activating the fallback model from the UI to the core, which improves the separation of concerns. The introduction of the ModelChanged event and its handling in GeminiClient to reset the sequence model is a clean solution to ensure routing is re-evaluated. The addition of a specific test case for re-routing within the same prompt is excellent and provides confidence in the fix. Furthermore, the inclusion of dispose methods for cleanup is a good practice for resource management. Overall, this is a high-quality contribution that improves both functionality and code structure.
gemini-cli
bot
added
the
status/need-issue
|
/patch preview |
|
✅ Patch workflow(s) dispatched successfully! 📋 Details:
🔗 Track Progress: |
2 participants
Summary
Fixes fallback behavior so switching to Flash persists within the same prompt and across continuations.
Core fallback now owns the model switch, and GeminiClient clears the sticky sequence model when the configured model changes, ensuring routing re-evaluates after fallback.
Details
Related Issues
How to Validate
Select Auto, Trigger Pro quota exceeded error, select fallback to flash, confirm that the turn and subsequent prompts use flash.
Pre-Merge Checklist